检索结果-内蒙古大学图书馆

optimization of Reservoir Operation using New Hybrid algorithm

KSCE JOURNAL OF CIVIL ENGINEERING 2018年第11期22卷 4668-4680页

作者： Yaseen, Zaher Mundher Karami, Hojat Ehteram, Mohammad Mohd, Nuruol Syuhadaa Mousavi, Sayed Farhad Hin, Lai Sai Kisi, Ozgur Farzin, Saeed Kim, Sungwon El-Shafie, Ahmed Ton Duc Thang Univ Fac Civil Engn Ho Chi Minh City Vietnam Semnan Univ Dept Water Engn & Hydraul Struct Fac Civil Engn Semnan Iran Univ Malaya Civil Engn Dept Fac Engn Kuala Lumpur 50603 Malaysia Ilia State Univ Sch Nat Sci & Engn Tbilisi Georgia Dongyang Univ Dept Railrd Construct & Safety Engn Yeongju 36040 South Korea

Due to the scarcity of fresh water resources, exploiting dams' reservoirs, based on their optimal operation, obviates construction of extra dams and high costs and satisfies downstream consumers' water needs with high reliability. In this research, a new hybrid approach of Artificial Fish swarm algorithm (AFSA) and particle swarm optimization algorithm (PSOA) is used to optimize Karun-4 reservoir, increase energy production and minimize downstream water shortages. This Hybrid algorithm (HA) brings about diversity of responses in PSOA, prevents entrapment of AFSA in local optimum traps and increases convergence speed and balances between the abilities to scan and make profit in the AFSA. This method was assessed based on reliability, vulnerability and resilience indices. In addition, based on a multi-criteria decision-making model, it was evaluated by comparing it with other evolutionary algorithms. To verify the HA, it was tested on few mathematical functions. Results indicated that the HA features performed higher reliability, lower vulnerability and resiliency, as compared with AFSA and PSOA. In addition, HA is ranked first according to the multi criteria decision making model. Further, among all the tested evolutionary methods, this new algorithm yielded the best answer for dam power plant's objective function.

关键词： optimization of reservoir operation artificial intelligence artificial fish algorithm particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Inverse Analysis of Various Surface Emissivity Distributions with particle swarm optimization Method

引用

TRANSACTIONS OF THE KOREAN SOCIETY OF MECHANICAL ENGINEERS B 2018年第9期42卷 573-582页

作者： Lee, Kyun Ho Sejong Univ Dept Aerosp Engn Sch Mech & Aerosp Engn Seoul South Korea

Generally, thermal radiation heat transfer can be classified into two forms, surface and gas radiation, depending on the participation of the medium in the heat transfer process. The objective of the present study is to estimate the unknown surface emissivities of various profiles by the inverse analysis of the pure surface radiation problem. To do this, an axisymmetric cylindrical enclosure is considered and the particle swarm optimization (PSO) method is employed as an inverse solver to find the exact solutions efficiently. By comparing the convergence rates and accuracies of the obtained results, the present study intends to discuss the feasibility of the PSO method as the inverse solver of the surface radiation problem involving multi-parameter unknowns.

关键词： Inverse Analysis Surface Radiation Surface Emissivity particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of an improved minimum entropy deconvolution method for railway rolling element bearing fault diagnosis

引用

JOURNAL OF SOUND AND VIBRATION 2018年 425卷 53-69页

作者： Cheng, Yao Zhou, Ning Zhang, Weihua Wang, Zhiwei Southwest Jiaotong Univ State Key Lab Tract Power Chengdu 610031 Sichuan Peoples R China

Minimum entropy deconvolution is a widely-used tool in machinery fault diagnosis, because it enhances the impulse component of the signal. The filter coefficients that greatly influence the performance of the minimum entropy deconvolution are calculated by an iterative procedure. This paper proposes an improved deconvolutionmethod for the fault detection of rolling element bearings. The proposed method solves the filter coefficients by the standard particle swarm optimization algorithm, assisted by a generalized spherical coordinate transformation. When optimizing the filters performance for enhancing the impulses in fault diagnosis (namely, faulty rolling element bearings), the proposed method outperformed the classical minimum entropy deconvolution method. The proposed method was validated in simulation and experimental signals from railway bearings. In both simulation and experimental studies, the proposed method delivered better deconvolution performance than the classical minimum entropy deconvolutionmethod, especially in the case of low signal-to-noise ratio. (c) 2018 Published by Elsevier Ltd.

关键词： Minimum entropy deconvolution particle swarm optimization algorithm Fault diagnosis Railway Rolling element bearing

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimal Sensor Placement for Low-Pressure Gas Distribution Networks

引用

IEEE SENSORS JOURNAL 2018年第16期18卷 6660-6668页

作者： Zan, Thaw Tar Thein Gupta, Payal Wang, Mengmeng Dauwels, Justin Ukil, Abhisek Nanyang Technol Univ ERIAN Energy Res Inst Singapore 639798 Singapore Digital Money Myanmar Yangon Myanmar Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore Univ Auckland Dept Elect & Comp Engn Auckland 1010 New Zealand

Natural gas distribution systems are inherently vulnerable to accidental or intentional intrusion. Such events lead to financial losses and endanger the environmental and public safety. Therefore, it is crucial to adequately monitor the gas distribution systems. An important step toward this goal is to optimize the placement of sensors in the network. In this paper, we propose three design objectives including time-to-detection (TTD), sensitivity, and impact propagation (IP) and implement five multi-objective optimization algorithms (greedy, greedy randomized adaptive search procedure, non-dominated sorting genetic algorithm II, FrameSense, and particle swarm optimization (PSO)) to strategically place the sensors. From the results on an artificial network with 37 nodes and 50 branches and a real network in Singapore with 148 nodes and 150 branches, we find that Greedy and PSO algorithms are almost 10 times faster than the other algorithms in computational time. We also investigate the tradeoff between the design objectives and the number of sensors. Since TTD, sensitivity, and IP have different measurement units, we normalize their values within 0 to 1 (0%-100%) and consider the average of those three normalized values as the design cost. For 10% design cost, the number of required sensors is 5 and 8 for the artificial network and the real network, respectively. The results indicate that PSO yields the sensor configuration with the lowest design cost and the computational time.

关键词： Sensor placement multi-objective optimization FrameSense genetic algorithm GRASP greedy algorithm particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Novel optical efficiency formulas for parabolic trough solar collectors: Computing method and applications

引用

APPLIED ENERGY 2018年 224卷 682-697页

作者： Cheng, Ze-Dong Zhao, Xue-Ru He, Ya-Ling Xi An Jiao Tong Univ Sch Energy & Power Engn Key Lab Thermofluid Sci & Engn Minist Educ Xian 710049 Shaanxi Peoples R China

This paper presents a novel computing method of optical efficiency fitting formulas and its applications for parabolic trough solar collectors, by combining the Monte Carlo ray-tracing methodology with the population based particle swarm optimization algorithm. The expressions of the optical efficiency fitting formulas are deduced by means of analyzing the Monte Carlo ray-tracing data samples with a variable reduction technique, while the fitting formula coefficients are obtained using the particle swarm optimization algorithm. The computing time of the annual optical efficiency reduces to less than 10(-7) s, from about a day as previously calculated by a once powerful Monte Carlo ray-tracing model. Thus, it makes the once time-consuming long-time average optical efficiency calculations or corresponding population-based optimizations much more feasible and efficient. A dynamic particle swarm size factor is also proposed to improve the particle swarm optimization performance, which reduces nearly 90% of the particle swarm optimization computing time. Numerical results calculated by the Monte Carlo ray-tracing model and the obtained optical efficiency fitting formulas were compared with the corresponding reference data. Good agreements were obtained, proving that the computing method and model are reliable. The obtained optical efficiency fitting formula of parabolic trough solar collectors is then applied successfully to efficiently study the characteristics of long-time average optical efficiencies under different geometrical configurations, geographical locations, tracking models and corresponding optical or geometrical optimizations. This proposed novel method offers a useful option of high potential for further applications on efficient optical efficiency related analyses and corresponding population-based optimizations for parabolic trough solar collectors.

关键词： Parabolic trough solar collector Optical efficiency Fitting formula Monte Carlo ray-tracing particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A fuzzy logic-based method for solving the scheduling problem in the cloud environments using a non-dominated sorted algorithm

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2019年第17期31卷

作者： Wakil, Karzan Badfar, Arshad Dehghani, Pooyan Sadati, Seyed Mojtaba Shoja Navimipour, Nima Jafari Sulaimani Polytech Univ Res Ctr Sulaimani Iraq Islamic Azad Univ Dept Comp Engn Cent Tehran Branch Tehran Iran Islamic Azad Univ Dept Ind Management South Tehran Branch Tehran Iran Shahid Beheshti Univ Elect Engn Dept Tehran Iran Islamic Azad Univ Islamshahr Branch Young Researchers & Elite Club Islamshahr *** Iran

Cloud computing as a new model of delivering IT services on the Internet has attained high attention recently. In this new paradigm, efficient service management causes the high quality of provided services. Scheduling as one of the most important duties of service management is a key problem in cloud computing that affects the total system performance. In most cases, the meta-heuristic methods are used for optimizing the scheduling issues instead of traditional methods. One of the influential evolutionary algorithms for optimizing the complicated problems is a non-dominated sorting particle swarm optimization (NSPSO) technique. In this paper, we propose a meta-heuristic technique using the NSPSO model for decreasing total cost and consumed total time. Furthermore, fuzzy set theory is applied to select the best solution. Simulation results have indicated that the efficiency of NSPSO is improved. In the many types of experiment, the proposed NSPSO algorithm was appropriate to keep a good spread of solutions and good converge. In addition, the diversity preserving mechanism applied in NSPSO has improvement against the other two investigated algorithms.

关键词： cloud computing multi-objective optimization particle swarm optimization algorithm task scheduling

来源：评论

学校读者我要写书评

暂无评论

Optimized radial basis function neural network for improving approximate dynamic programming in pricing high dimensional options

引用

NEURAL COMPUTING & APPLICATIONS 2018年第6期30卷 1783-1794页

作者： Hajizadeh, Ehsan Mahootchi, Masoud Amirkabir Univ Technol Tehran Polytech Dept Ind Engn & Management Syst 424 Hafez Ave Tehran *** Iran

Pricing American basket option is one of the essential problems in quantitative finance. The complexity of this type of option has motivated many practitioners and researchers to develop simulation-based methods. In this paper, we develop an optimized radial basis function neural network (RBFNN), which is optimally tuned by the particle swarm optimization algorithm to enhance the efficiency and accuracy of approximate dynamic programming (ADP) for pricing the American basket option. Additionally, for the scenario generation, a simulation-based technique using a copula-GARCH method and Extreme Value Theory is performed to tackle the nonlinearity of dependencies between variables. The prices obtained through the proposed approach compared with those ones achieved from pure RBFNN and ADP in different situations. This is also illustrated that the obtained prices of American basket option can outperform the results obtained through the RBFNN and ADP approaches in terms of the predefined fitness measures.

关键词： Radial basis function neural network Approximate dynamic programming particle swarm optimization algorithm American basket options

来源：评论

学校读者我要写书评

暂无评论

optimization of a heliostat field layout using hybrid PSO-GA algorithm

引用

APPLIED THERMAL ENGINEERING 2018年 128卷 33-41页

作者： Li, Chao Zhai, Rongrong Liu, Hongtao Yang, Yongping Wu, Hao North China Elect Power Univ Sch Energy Power & Mech Engn Beijing 102206 Peoples R China

A mathematical model of the heliostat field and the PSO-GA algorithm are developed in Matlab to optimize a heliostat field and determine the highest potential daily energy collection (DEC). The heliostat field in Lhasa, China is analyzed as an example. The energy collected per unit cost (ECUC) is then calculated to evaluate the economic performance of the heliostat field. Furthermore, the effects of several important factors on the heliostat field are also explored. Results indicate that, after optimization, the DEC during the spring equinox, summer solstice, autumnal equinox, and winter solstice increase by approximately 1.1 x 10(5), 1.8 x 10(5), 1.2 x 10(5), and 0.9 x 10(5) MJ, respectively. Studies on the key parameters show that as the number of heliostats in the first row of the field (Nhel(1)) increases, the ECUC first increases to its maximum value and then decreases. Additionally, ECUC increases with tower height but decreases as the cost of the heliostat mirror collector increases. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Solar tower power system Heliostat field optimization Genetic algorithm particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A swarm Intelligence algorithm for Routing Recovery Strategy in Wireless Sensor Networks With Mobile Sink

引用

IEEE ACCESS 2018年 6卷 67434-67445页

作者： Yue, Yinggao Cao, Li Hang, Bo Luo, Zhongqiang Hubei Univ Arts & Sci Comp Sch Xiangyang 441053 Peoples R China Sichuan Univ Sci & Engn Artificial Intelligence Key Lab Sichuan Prov Yibin 644000 Peoples R China Southwest Univ Sci & Technol Sch Informat Engn Mianyang 621010 Peoples R China

Considering the fault tolerance mechanism in the route optimization of the mobile wireless sensor network (MWSN), we analyze the routing fault tolerance between nodes and establish an intelligent fault-tolerant routing model for MWSN. We also propose a novel fault-tolerant routing algorithm for an MWSN based on an artificial bee colony (ABC) optimized particle swarm optimization algorithm (ABC-PSO), and this optimizes the ABC-PSO algorithm is applied to study the optimal construction strategy of an alternate route. The proposed using of the path coding, the ABC algorithm optimization, the collaborative updation, and the evolution of the principal and subordinate swarms, as well as particle selection, provide faster overall convergence performance and more accurate solutions for the network optimization. Analytical proofs and simulation experiments show that the route fault-tolerant strategy proposed in this paper can create a reliable transmission environment and an efficient route recovery mechanism for the MWSN. Moreover, it can lower the energy consumption of the network and increase the network's lifetime and improve the robustness and the reliability of MWSN.

关键词： Mobile wireless sensor networks fault tolerant swarm intelligence algorithm particle swarm optimization algorithm reliability

来源：评论

学校读者我要写书评

暂无评论

optimization and performance analysis of solar hybrid CCHP systems under different operation strategies

引用

APPLIED THERMAL ENGINEERING 2018年 133卷 327-340页

作者： Yang, Gan Zhai, Xiaoqiang Shanghai Jiao Tong Univ Inst Refrigerat & Cryogen Shanghai 200240 Peoples R China

The hybridization between conventional combined cooling heating and power (CCHP) systems and solar systems has been considered as a good solution to the urgent energy and environment issues. This study develops the mathematical model of a CCHP system hybridized with PV panels and solar thermal collectors. The particle swarm optimization (PSO) algorithm is adopted to find the optimum values of design parameters. Based on the energy output characteristic of the solar hybrid CCHP system, five operation strategies of the conventional CCHP system are adjusted and applied for the solar hybrid CCHP system. The simulation work of the hybrid CCHP systems based upon a hotel building in Atlanta is carried out to find an appropriate design scheme. The results show that the hybrid CCHP system under the FEL-ECR mode is the best choice. Besides, its PESR, CO2ERR and ATCSR can reach 36.15%, 53.73% and 4.16%, respectively. Compared with a conventional CCHP system, the hybrid CCHP system achieves better energy-saving and CO2 reduction performance. However, the hybrid CCHP system consumes more annual total costs because of its high initial investment.

关键词： Combined cooling heating and power Solar energy Hybrid system particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：